{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,24]],"date-time":"2025-05-24T04:02:26Z","timestamp":1748059346205,"version":"3.41.0"},"publisher-location":"Cham","reference-count":57,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031925900","type":"print"},{"value":"9783031925917","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-92591-7_14","type":"book-chapter","created":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T07:24:22Z","timestamp":1747985062000},"page":"218-235","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["VLM-HOI: Vision Language Models for\u00a0Interpretable Human-Object Interaction Analysis"],"prefix":"10.1007","author":[{"given":"Donggoo","family":"Kang","sequence":"first","affiliation":[]},{"given":"Dasol","family":"Jeong","sequence":"additional","affiliation":[]},{"given":"Hyunmin","family":"Lee","sequence":"additional","affiliation":[]},{"given":"Sangwoo","family":"Park","sequence":"additional","affiliation":[]},{"given":"Hasil","family":"Park","sequence":"additional","affiliation":[]},{"given":"Sunkyu","family":"Kwon","sequence":"additional","affiliation":[]},{"given":"Yeongjoon","family":"Kim","sequence":"additional","affiliation":[]},{"given":"Joonki","family":"Paik","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,5,12]]},"reference":[{"key":"14_CR1","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Antol, S., et al.: VQA: visual question answering. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2425\u20132433 (2015)","DOI":"10.1109\/ICCV.2015.279"},{"issue":"2","key":"14_CR3","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","volume":"41","author":"T Baltru\u0161aitis","year":"2019","unstructured":"Baltru\u0161aitis, T., Ahuja, C., Morency, L.P.: Multimodal machine learning: a survey and taxonomy. IEEE Trans. Pattern Anal. Mach. Intell. 41(2), 423\u2013443 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"14_CR4","first-page":"1877","volume":"33","author":"T Brown","year":"2020","unstructured":"Brown, T., et al.: Language models are few-shot learners. Adv. Neural. Inf. Process. Syst. 33, 1877\u20131901 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision, pp. 213\u2013229. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Chen, J., Yanai, K.: QAHOI: query-based anchors for human-object interaction detection. In: 2023 18th International Conference on Machine Vision and Applications (MVA), pp.\u00a01\u20135. IEEE (2023)","DOI":"10.23919\/MVA57639.2023.10215534"},{"key":"14_CR7","unstructured":"Chen, X., Fang, H., Lin, T.Y., Vedantam, R., Gupta, S., Dollar, P., Zitnick, C.L.: Microsoft coco captions: Data collection and evaluation server. arXiv preprint arXiv:1504.00325 (2015)"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Y.C., et al.: UNITER: universal image-text representation learning. In: European Conference on Computer Vision, pp. 104\u2013120. Springer (2020)","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"14_CR9","unstructured":"Chowdhery, A., et\u00a0al.: PaLM: Scaling language modeling with pathways. arXiv preprint arXiv:2204.02311 (2022)"},{"key":"14_CR10","unstructured":"Dai, W., et al.: InstructBLIP: Towards general-purpose vision-language models with instruction tuning (2023)"},{"key":"14_CR11","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"14_CR12","unstructured":"Gao, C., Zou, Y., Huang, J.B.: iCAN: instance-centric attention network for human-object interaction detection. In: British Machine Vision Conference (2018)"},{"key":"14_CR13","unstructured":"Gupta, S., Malik, J.: Visual semantic role labeling. arXiv preprint arXiv:1505.04474 (2015)"},{"key":"14_CR14","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"584","DOI":"10.1007\/978-3-030-58555-6_35","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Z Hou","year":"2020","unstructured":"Hou, Z., Peng, X., Qiao, Yu., Tao, D.: Visual compositional learning for human-object interaction detection. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12360, pp. 584\u2013600. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58555-6_35"},{"key":"14_CR15","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Fei-Fei, L.: Deep visual-semantic alignments for generating image descriptions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3128\u20133137 (2015)","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Kim, B., Lee, J., Kang, J., Kim, E.S., Kim, H.J.: HOTR: end-to-end human-object interaction detection with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 74\u201383 (2021)","DOI":"10.1109\/CVPR46437.2021.00014"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Kim, B., Mun, J., On, K.W., Shin, M., Lee, J., Kim, E.S.: MSTR: multi-scale transformer for end-to-end human-object interaction detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19578\u201319587 (2022)","DOI":"10.1109\/CVPR52688.2022.01897"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Kim, S., Jung, D., Cho, M.: Relational context learning for human-object interaction detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2925\u20132934 (2023)","DOI":"10.1109\/CVPR52729.2023.00286"},{"key":"14_CR19","unstructured":"Kiros, R., Salakhutdinov, R., Zemel, R.S.: Unifying visual-semantic embeddings with multimodal neural language models. In: arXiv preprint arXiv:1411.2539 (2014)"},{"key":"14_CR20","unstructured":"Li, J., Li, D., Savarese, S., Hoi, S.: BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)"},{"key":"14_CR21","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning, pp. 12888\u201312900. PMLR (2022)"},{"key":"14_CR22","first-page":"9694","volume":"34","author":"J Li","year":"2021","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.: Align before fuse: vision and language representation learning with momentum distillation. Adv. Neural. Inf. Process. Syst. 34, 9694\u20139705 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR23","unstructured":"Li, L.H., Yatskar, M., Yin, D., Hsieh, C.J., Chang, K.W.: VisualBERT: A simple and performant baseline for vision and language. arXiv preprint arXiv:1908.03557 (2019)"},{"key":"14_CR24","first-page":"5011","volume":"33","author":"YL Li","year":"2020","unstructured":"Li, Y.L., Liu, X., Wu, X., Li, Y., Lu, C.: HOI analysis: integrating and decomposing human-object interaction. Adv. Neural. Inf. Process. Syst. 33, 5011\u20135022 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Liao, Y., Liu, S., Wang, F., Chen, Y., Qian, C., Feng, J.: PPDM: parallel point detection and matching for real-time human-object interaction detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 482\u2013490 (2020)","DOI":"10.1109\/CVPR42600.2020.00056"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Liao, Y., Zhang, A., Lu, M., Wang, Y., Li, X., Liu, S.: GEN-VLKT: simplify association and enhance interaction understanding for hoi detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20123\u201320132 (2022)","DOI":"10.1109\/CVPR52688.2022.01949"},{"key":"14_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"14_CR28","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)"},{"key":"14_CR29","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"14_CR30","doi-asserted-by":"crossref","unstructured":"Lu, J., Goswami, V., Rohrbach, M., Parikh, D., Lee, S.: 12-in-1: multi-task vision and language representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10437\u201310446 (2019)","DOI":"10.1109\/CVPR42600.2020.01045"},{"key":"14_CR31","doi-asserted-by":"crossref","unstructured":"Ma, S., Wang, Y., Wang, S., Wei, Y.: FGAHOI: Fine-grained anchors for human-object interaction detection. arXiv preprint arXiv:2301.04019 (2023)","DOI":"10.1109\/TPAMI.2023.3331738"},{"key":"14_CR32","doi-asserted-by":"crossref","unstructured":"Ning, S., Qiu, L., Liu, Y., He, X.: HOICLIP: efficient knowledge transfer for hoi detection with vision-language models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 23507\u201323517 (2023)","DOI":"10.1109\/CVPR52729.2023.02251"},{"key":"14_CR33","unstructured":"OpenAI: GPT-4 technical report (2023)"},{"key":"14_CR34","doi-asserted-by":"crossref","unstructured":"Park, J., Park, J.W., Lee, J.S.: ViPLO: vision transformer based pose-conditioned self-loop graph for human-object interaction detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 17152\u201317162 (2023)","DOI":"10.1109\/CVPR52729.2023.01645"},{"key":"14_CR35","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"14_CR36","unstructured":"Su, W., et al.: VL-BERT: Pre-training of generic visual-linguistic representations. arXiv preprint arXiv:1908.08530 (2019)"},{"key":"14_CR37","doi-asserted-by":"crossref","unstructured":"Tamura, M., Ohashi, H., Yoshinaga, T.: QPIC: query-based pairwise human-object interaction detection with image-wide contextual information. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10410\u201310419 (2021)","DOI":"10.1109\/CVPR46437.2021.01027"},{"key":"14_CR38","doi-asserted-by":"crossref","unstructured":"Tan, H., Bansal, M.: LXMERT: Learning cross-modality encoder representations from transformers. In: arXiv preprint arXiv:1908.07490 (2019)","DOI":"10.18653\/v1\/D19-1514"},{"key":"14_CR39","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"14_CR40","unstructured":"Wang, T., Yang, T., Danelljan, M., Khan, F.S., Zhang, X., Sun, J.: IPNET. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4116\u20134125 (2020)"},{"key":"14_CR41","doi-asserted-by":"crossref","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified perceptual parsing for scene understanding. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 418\u2013434 (2018)","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"14_CR42","doi-asserted-by":"crossref","unstructured":"Xie, X., Bhatnagar, B.L., Pons-Moll, G.: Visibility aware human-object interaction tracking from single RGB camera. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4757\u20134768 (2023)","DOI":"10.1109\/CVPR52729.2023.00461"},{"key":"14_CR43","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"key":"14_CR44","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a032 (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"14_CR45","doi-asserted-by":"crossref","unstructured":"Yao, T., Pan, Y., Li, Y., Mei, T.: Exploring visual relationship for image captioning. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 684\u2013699 (2018)","DOI":"10.1007\/978-3-030-01264-9_42"},{"key":"14_CR46","unstructured":"Yu, J., Wang, Z., Vasudevan, V., Yeung, L., Seyedhosseini, M., Wu, Y.: CoCa: Contrastive captioners are image-text foundation models. arXiv preprint arXiv:2205.01917 (2022)"},{"key":"14_CR47","first-page":"37416","volume":"35","author":"H Yuan","year":"2022","unstructured":"Yuan, H., et al.: RLIP: relational language-image pre-training for human-object interaction detection. Adv. Neural. Inf. Process. Syst. 35, 37416\u201337431 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR48","doi-asserted-by":"crossref","unstructured":"Yuan, H., et al.: RLIPv2: fast scaling of relational language-image pre-training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 21649\u201321661 (2023)","DOI":"10.1109\/ICCV51070.2023.01979"},{"key":"14_CR49","first-page":"17209","volume":"34","author":"A Zhang","year":"2021","unstructured":"Zhang, A., et al.: Mining the benefits of two-stage and one-stage HOI detection. Adv. Neural. Inf. Process. Syst. 34, 17209\u201317220 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR50","doi-asserted-by":"crossref","unstructured":"Zhang, F.Z., Campbell, D., Gould, S.: Spatially conditioned graphs for detecting human-object interactions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13319\u201313327 (2021)","DOI":"10.1109\/ICCV48922.2021.01307"},{"key":"14_CR51","doi-asserted-by":"crossref","unstructured":"Zhang, F.Z., Campbell, D., Gould, S.: Efficient two-stage detection of human-object interactions with a novel unary-pairwise transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20104\u201320112 (2022)","DOI":"10.1109\/CVPR52688.2022.01947"},{"key":"14_CR52","doi-asserted-by":"crossref","unstructured":"Zhang, F.Z., Yuan, Y., Campbell, D., Zhong, Z., Gould, S.: Exploring predicate visual context in detecting of human-object interactions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10411\u201310421 (2023)","DOI":"10.1109\/ICCV51070.2023.00955"},{"key":"14_CR53","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Pan, Y., Yao, T., Huang, R., Mei, T., Chen, C.W.: Exploring structure-aware transformer over interaction proposals for human-object interaction detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19548\u201319557 (2022)","DOI":"10.1109\/CVPR52688.2022.01894"},{"key":"14_CR54","doi-asserted-by":"crossref","unstructured":"Zhong, X., Qu, X., Ding, C., Tao, D.: Glance and gaze: inferring action-aware points for one-stage human-object interaction detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13234\u201313243 (2021)","DOI":"10.1109\/CVPR46437.2021.01303"},{"key":"14_CR55","doi-asserted-by":"crossref","unstructured":"Zhou, D., et al.: Human-object interaction detection via disentangled transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19568\u201319577 (2022)","DOI":"10.1109\/CVPR52688.2022.01896"},{"key":"14_CR56","doi-asserted-by":"crossref","unstructured":"Zhou, L., Palangi, H., Zhang, L., Hu, H., Corso, J., Gao, J.: Unified vision-language pre-training for image captioning and VQA. In: Proceedings of the AAAI Conference on Artificial Intelligence. vol.\u00a034, pp. 13041\u201313049 (2020)","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"14_CR57","doi-asserted-by":"crossref","unstructured":"Zou, C., et\u00a0al.: End-to-end human object interaction detection with hoi transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11825\u201311834 (2021)","DOI":"10.1109\/CVPR46437.2021.01165"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024 Workshops"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-92591-7_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,23]],"date-time":"2025-05-23T07:24:59Z","timestamp":1747985099000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-92591-7_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031925900","9783031925917"],"references-count":57,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-92591-7_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"12 May 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}